From d0bd1e5c8eea0021fbc677a9e451fe0b4fc8d910 Mon Sep 17 00:00:00 2001 From: Reuben Morais Date: Tue, 30 Jun 2020 20:01:44 +0200 Subject: [PATCH] Add more doc text around distinction between various pre-trained model files --- doc/USING.rst | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/doc/USING.rst b/doc/USING.rst index db3013d8..2d874ba1 100644 --- a/doc/USING.rst +++ b/doc/USING.rst @@ -40,6 +40,20 @@ If you want to use the pre-trained English model for performing speech-to-text, wget https://github.com/mozilla/DeepSpeech/releases/download/v0.7.4/deepspeech-0.7.4-models.pbmm wget https://github.com/mozilla/DeepSpeech/releases/download/v0.7.4/deepspeech-0.7.4-models.scorer +There are several pre-trained model files available in official releases. Files ending in ``.pbmm`` are compatible with clients and language bindings built against the standard TensorFlow runtime. Usually these packages are simply called ``deepspeech``. These files are also compatible with CUDA enabled clients and language bindings. These packages are usually called ``deepspeech-gpu``. Files ending in ``.tflite`` are compatible with clients and language bindings built against the `TensorFlow Lite runtime `_. These models are optimized for size and performance in low power devices. On desktop platforms, the compatible packages are called ``deepspeech-tflite``. On Android and Raspberry Pi, we only publish TensorFlow Lite enabled packages, and they are simply called ``deepspeech``. You can see a full list of supported platforms and which TensorFlow runtime is supported at :ref:`supported-platforms-inference`. + ++--------------------+---------------------+---------------------+ +| Package/Model type | .pbmm | .tflite | ++====================+=====================+=====================+ +| deepspeech | Depends on platform | Depends on platform | ++--------------------+---------------------+---------------------+ +| deepspeech-gpu | ✅ | ❌ | ++--------------------+---------------------+---------------------+ +| deepspeech-tflite | ❌ | ✅ | ++--------------------+---------------------+---------------------+ + +Finally, the pre-trained model files also include files ending in ``.scorer``. These are external scorers (language models) that are used at inference time in conjunction with an acoustic model (``.pbmm`` or ``.tflite`` file) to produce transcriptions. We also provide further documentation on :ref:`the decoding process ` and :ref:`how language models are generated `. + Model compatibility ^^^^^^^^^^^^^^^^^^^